Traditionally, time-lapse videos are constructed from images captured at given time intervals called “temporal points of interests” or “temporal POIs.” Disclosed herein are intelligent systems and methods of capturing and selecting better images around temporal points of interest for the construction of improved time-lapse videos. According to some embodiments, a small “burst” of images may be captured, centered around the aforementioned temporal points of interest. Then, each burst sequence of images may be analyzed, e.g., by performing a similarity comparison between each image in the burst sequence and the image selected at the previous temporal point of interest. Selecting the image from a given burst that is most similar to the previous selected image allows the intelligent systems and methods described herein to improve the quality of the resultant time-lapse video by discarding “outlier” or other undesirable images captured in the burst sequence around a particular temporal point of interest.